code-review

code-review is a skill for Claude Code, Codex from iampawan/Manifest. It costs 71 tokens per session (3,571 once invoked), scanned A, original, MIT.

A code-focused pull-request review that looks for security, correctness, performance, maintainability, and style problems in the implementation itself.

In plain words
What is it for?
Use it after implementation to review a PR and post findings labeled as blockers, warnings, or information. It complements checks that only compare code with the feature contract.
Why use it?
It catches code defects that a requirements check may miss, such as security holes, bugs, slow patterns, or hard-to-maintain changes.

Skill for Claude CodeCodex

Part of the manifest plugin — 28 skills, 15 commands shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/iampawan/manifest/code-review
Any agent
npx skills add iampawan/Manifest --skill code-review
Clone the repo
git clone --depth 1 https://github.com/iampawan/Manifest

Made for: Claude Code, Codex.

Or install manifest, the plugin that ships this one along with the rest of its 28 skills, 15 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/iampawan/manifest/code-review.svg)](https://agentmods.dev/skills/iampawan/manifest/code-review)
Your own site
<a href="https://agentmods.dev/skills/iampawan/manifest/code-review"><img src="https://agentmods.dev/badge/skills/iampawan/manifest/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00071 $0.03571
Opus 5 $0.00036 $0.01785
Sonnet 5 $0.00014 $0.00714
Haiku 4.5 $0.00007 $0.00357

Measured 4d ago against content hash 69901cb3ab64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/code-review/SKILL.md · 316 lines

How it starts

The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code-review agent (PR stage)

You review the code in a pull request, not the contract. This is a different job from verify-pr:

  • verify-pr answers "did they build the thing the contract asked for?" — AC coverage, instrumentation events fired, flag gate present, no hardcoded strings.
  • code-review (you) answers "is the code itself sound?" — security holes, correctness bugs, performance traps, and maintainability rot that AC-conformance never catches.

Both run on the PR. Neither replaces the other. Production bugs that slip past spec-conformance almost always live in your half.

Severity + output

Protocol: reuse the closed severity enum from the compact reference/CRITIC-RULES.mdblocker | warning | info, and ONLY those. Do not invent "high"/"medium"/"critical"; the validator (scripts/validate.mjs --check-review) rejects them and the run fails.

Your output is a JSON array. Each element MUST match this schema (it's checked deterministically — out-of-schema output is a bug, not a finding):

[
  {
    "id": "CR-001",
    "category": "security | correctness | performance | maintainability | style",
    "severity": "blocker | warning | info",
    "message": "one-line statement of the defect",
    "suggestion": "concrete code change that fixes it",
    "file": "repo-relative path, e.g. src/checkout/SavedCardRow.tsx",
    "line": 142,
    "status": "open"
  }
]

line may be null if the finding is file- or PR-wide. id must use the CR- prefix. Validate before posting:

node <plugin-root>/scripts/validate.mjs --check-review <findings.json>

Exit code 2 means open blockers exist — CI uses that to gate the merge.

What each severity means here

  • blocker — would cause a production incident or a security/data breach if merged: injection, broken authz, secret in the diff, a crash on a common path, data loss, an unbounded query on a hot path.
  • warning — a real defect that should be fixed but won't take prod down on its own: a missing error branch on a rare path, an N+1 that's small today, a race that needs an unlikely interleaving.
  • info — style, naming, a cleaner idiom, a maintainability nit.

Read the full file on GitHub · 316 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 316 lines · 71 tokens per session scan A 69901cb3ab64

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository iampawan/Manifest (5 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 3,571 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens